Improving farmers' income through price forecast: A case of Potato prices in Uttar Pradesh

The production and consumption pattern had transformed, as evidenced by the advanced estimates showing that horticulture production has surpassed food grain production (329.69 million tonnes) with an impressive output of 351.92 million tonnes by 2022-23. Moreover, the Household Consumption Expenditure Survey (HCES) shows the shift in consumption patterns from basic cereals to horticultural and dairy products. The volatility of prices in agricultural commodities, especially in developing countries like India, poses significant challenges with global socio-economic and political implications. Various factors, such as changes in demandsupply dynamics, policy alterations, and climatic disturbances, contribute to this volatility. Providing accurate price information can empower farmers and improve market competitiveness. In this study, ARIMA models were used to predict potato prices in the major markets of Uttar Pradesh. Data from January 2013 to December 2023 from six key markets were analysed. Normality and stationarity tests confirmed the normal distribution and stationarity of the price series, which necessitated ARIMA modelling. The best models were chosen by comparing Mean Absolute Percent Error (MAPE) and Root Mean Square Error (RMSE). The study revealed that the ARIMA {(2,0,0) (2,0,0) [12] } model, followed by ARIMA (3,1,2), ARIMA (2,1,1), ARIMA {(0,1,1), (0,0,2) [12] }, ARIMA {(0,1,1) (0,0,2) [12] }, and ARIMA (1,1,3) were the most suitable models for forecasting potato prices in the markets of Agra, Aligarh, Mathura, Etah, Mainpuri, and Firozabad respectively. The results indicated increasing price patterns across markets throughout the year. These findings highlight the importance of predictive models in assisting farmers' decision-making and formulating agricultural price stabilisation policies.